{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-text-retrieval/papers/ran/1","list_of":"/task/image-text-retrieval","task":"Image-text Retrieval","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,49],"of":49,"counts":{"archive_papers_tagged":248,"with_a_code_link":131,"where_syntology_ran_a_sample":49,"not_listed_spam_title":0,"listed":248,"listed_where_code_ran":49,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":44,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":44,"listed_every_run_a_failure_of_syntologys_instrument":5,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/image-text-retrieval/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/fg-clip-fine-grained-visual-and-textual","slug":"fg-clip-fine-grained-visual-and-textual","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","date":"2025-05-08","arxiv_id":"2505.05071","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fg-clip-fine-grained-visual-and-textual#ran","syntology_url":"https://syntology.ai/paper/2505.05071","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05071"}},"official":{"repos":["360cvgroup/fg-clip"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mind-the-gap-benchmarking-spatial-reasoning","slug":"mind-the-gap-benchmarking-spatial-reasoning","title":"Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models","date":"2025-03-25","arxiv_id":"2503.19707","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mind-the-gap-benchmarking-spatial-reasoning#ran","syntology_url":"https://syntology.ai/paper/2503.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19707"}},"official":{"repos":["stogiannidis/srbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/med3dvlm-an-efficient-vision-language-model","slug":"med3dvlm-an-efficient-vision-language-model","title":"Med3DVLM: An Efficient Vision-Language Model for 3D Medical Image Analysis","date":"2025-03-25","arxiv_id":"2503.20047","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/med3dvlm-an-efficient-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.20047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20047"}},"official":{"repos":["mirthai/med3dvlm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/recon-enhancing-true-correspondence-1","slug":"recon-enhancing-true-correspondence-1","title":"ReCon: Enhancing True Correspondence Discrimination through Relation Consistency for Robust Noisy Correspondence Learning","date":"2025-02-27","arxiv_id":"2502.19962","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/recon-enhancing-true-correspondence-1#ran","syntology_url":"https://syntology.ai/paper/2502.19962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19962"}},"official":{"repos":["qxzha/ReCon"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/biomedica-an-open-biomedical-image-caption","slug":"biomedica-an-open-biomedical-image-caption","title":"BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature","date":"2025-01-13","arxiv_id":"2501.07171","repositories_listed":2,"syntology":{"n":20,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/biomedica-an-open-biomedical-image-caption#ran","syntology_url":"https://syntology.ai/paper/2501.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07171"}},"official":{"repos":["ale9806/open_clip_with_biomedica","minwoosun/biomedica-etl"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-label-cluster-discrimination-for-visual","slug":"multi-label-cluster-discrimination-for-visual","title":"Multi-label Cluster Discrimination for Visual Representation Learning","date":"2024-07-24","arxiv_id":"2407.17331","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-label-cluster-discrimination-for-visual#ran","syntology_url":"https://syntology.ai/paper/2407.17331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17331"}},"official":{"repos":["deepglint/unicom"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/object-aware-query-perturbation-for-cross","slug":"object-aware-query-perturbation-for-cross","title":"Object-Aware Query Perturbation for Cross-Modal Image-Text Retrieval","date":"2024-07-17","arxiv_id":"2407.12346","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/object-aware-query-perturbation-for-cross#ran","syntology_url":"https://syntology.ai/paper/2407.12346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12346"}},"official":{"repos":["nec-n-sogi/query-perturbation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/composing-object-relations-and-attributes-for-1","slug":"composing-object-relations-and-attributes-for-1","title":"Composing Object Relations and Attributes for Image-Text Matching","date":"2024-06-17","arxiv_id":"2406.11820","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/composing-object-relations-and-attributes-for-1#ran","syntology_url":"https://syntology.ai/paper/2406.11820","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11820"}},"official":{"repos":["vkhoi/cora_cvpr24"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rwkv-clip-a-robust-vision-language","slug":"rwkv-clip-a-robust-vision-language","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","date":"2024-06-11","arxiv_id":"2406.06973","repositories_listed":2,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/rwkv-clip-a-robust-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.06973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06973"}},"official":{"repos":["deepglint/rwkv-clip"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerating-transformers-with-spectrum-1","slug":"accelerating-transformers-with-spectrum-1","title":"Accelerating Transformers with Spectrum-Preserving Token Merging","date":"2024-05-25","arxiv_id":"2405.16148","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/accelerating-transformers-with-spectrum-1#ran","syntology_url":"https://syntology.ai/paper/2405.16148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16148"}},"official":{"repos":["hchautran/PiToMe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/m3d-advancing-3d-medical-image-analysis-with","slug":"m3d-advancing-3d-medical-image-analysis-with","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","date":"2024-03-31","arxiv_id":"2404.00578","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3d-advancing-3d-medical-image-analysis-with#ran","syntology_url":"https://syntology.ai/paper/2404.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00578"}},"official":{"repos":["baai-dcai/m3d"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dreamlip-language-image-pre-training-with","slug":"dreamlip-language-image-pre-training-with","title":"DreamLIP: Language-Image Pre-training with Long Captions","date":"2024-03-25","arxiv_id":"2403.17007","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dreamlip-language-image-pre-training-with#ran","syntology_url":"https://syntology.ai/paper/2403.17007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17007"}},"official":{"repos":["zyf0619sjtu/DreamLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/eye-gaze-guided-multi-modal-alignment","slug":"eye-gaze-guided-multi-modal-alignment","title":"Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning","date":"2024-03-19","arxiv_id":"2403.12416","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/eye-gaze-guided-multi-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2403.12416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12416"}},"official":{"repos":["momarky/egma"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/embracing-language-inclusivity-and-diversity","slug":"embracing-language-inclusivity-and-diversity","title":"Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning","date":"2024-01-30","arxiv_id":"2401.17186","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/embracing-language-inclusivity-and-diversity#ran","syntology_url":"https://syntology.ai/paper/2401.17186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17186"}},"official":{"repos":["yangbang18/clfm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/frozen-transformers-in-language-models-are","slug":"frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","arxiv_id":"2310.12973","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/frozen-transformers-in-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.12973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12973"}},"official":{"repos":["ziqipang/lm4visualencoding"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/alip-adaptive-language-image-pre-training","slug":"alip-adaptive-language-image-pre-training","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","date":"2023-08-16","arxiv_id":"2308.08428","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/alip-adaptive-language-image-pre-training#ran","syntology_url":"https://syntology.ai/paper/2308.08428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08428"}},"official":{"repos":["deepglint/alip"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/advclip-downstream-agnostic-adversarial","slug":"advclip-downstream-agnostic-adversarial","title":"AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning","date":"2023-08-14","arxiv_id":"2308.07026","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":10,"n_pointer_only":5,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 1 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/advclip-downstream-agnostic-adversarial#ran","syntology_url":"https://syntology.ai/paper/2308.07026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07026"}},"official":{"repos":["cgcl-codes/advclip"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/set-level-guidance-attack-boosting","slug":"set-level-guidance-attack-boosting","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","date":"2023-07-26","arxiv_id":"2307.14061","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":1,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"9 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/set-level-guidance-attack-boosting#ran","syntology_url":"https://syntology.ai/paper/2307.14061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.14061"}},"official":{"repos":["Zoky-2020/Set-level_Guidance_Attack"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/stop-pre-training-adapt-visual-language","slug":"stop-pre-training-adapt-visual-language","title":"Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages","date":"2023-06-29","arxiv_id":"2306.16774","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stop-pre-training-adapt-visual-language#ran","syntology_url":"https://syntology.ai/paper/2306.16774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16774"}},"official":{"repos":["yasminekaroui/clicotea"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-token-guided-image-text-retrieval","slug":"efficient-token-guided-image-text-retrieval","title":"Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training","date":"2023-06-15","arxiv_id":"2306.08789","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/efficient-token-guided-image-text-retrieval#ran","syntology_url":"https://syntology.ai/paper/2306.08789","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08789"}},"official":null}},{"url":"/paper/contrasting-intra-modal-and-ranking-cross","slug":"contrasting-intra-modal-and-ranking-cross","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","date":"2023-06-15","arxiv_id":"2306.08832","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrasting-intra-modal-and-ranking-cross#ran","syntology_url":"https://syntology.ai/paper/2306.08832","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08832"}},"official":{"repos":["lezhang7/Enhance-FineGrained","magiccircuit/enhance-finegrained"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/babel-imagenet-massively-multilingual","slug":"babel-imagenet-massively-multilingual","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","date":"2023-06-14","arxiv_id":"2306.08658","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/babel-imagenet-massively-multilingual#ran","syntology_url":"https://syntology.ai/paper/2306.08658","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.08658"}},"official":{"repos":["gregor-ge/babel-imagenet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/crossget-cross-guided-ensemble-of-tokens-for","slug":"crossget-cross-guided-ensemble-of-tokens-for","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers","date":"2023-05-27","arxiv_id":"2305.17455","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/crossget-cross-guided-ensemble-of-tokens-for#ran","syntology_url":"https://syntology.ai/paper/2305.17455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17455"}},"official":{"repos":["sdc17/crossget"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/s-clip-semi-supervised-vision-language-1","slug":"s-clip-semi-supervised-vision-language-1","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","date":"2023-05-23","arxiv_id":"2305.14095","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/s-clip-semi-supervised-vision-language-1#ran","syntology_url":"https://syntology.ai/paper/2305.14095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14095"}},"official":{"repos":["alinlab/s-clip"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":4,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}},"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/region-aware-pretraining-for-open-vocabulary","slug":"region-aware-pretraining-for-open-vocabulary","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","date":"2023-05-11","arxiv_id":"2305.07011","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/region-aware-pretraining-for-open-vocabulary#ran","syntology_url":"https://syntology.ai/paper/2305.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07011"}},"official":{"repos":["mcahny/rovit","google-research/google-research"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperbolic-image-text-representations","slug":"hyperbolic-image-text-representations","title":"Hyperbolic Image-Text Representations","date":"2023-04-18","arxiv_id":"2304.09172","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hyperbolic-image-text-representations#ran","syntology_url":"https://syntology.ai/paper/2304.09172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09172"}},"official":{"repos":["facebookresearch/meru"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["found_in_text","listed"]}}},{"url":"/paper/equivariant-similarity-for-vision-language","slug":"equivariant-similarity-for-vision-language","title":"Equivariant Similarity for Vision-Language Foundation Models","date":"2023-03-25","arxiv_id":"2303.14465","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}},"official":{"repos":["wangt-cn/eqben"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pmc-clip-contrastive-language-image-pre","slug":"pmc-clip-contrastive-language-image-pre","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","date":"2023-03-13","arxiv_id":"2303.07240","repositories_listed":2,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pmc-clip-contrastive-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2303.07240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.07240"}},"official":{"repos":["WeixiongLin/PMC-CLIP"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/uniadapter-unified-parameter-efficient","slug":"uniadapter-unified-parameter-efficient","title":"UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling","date":"2023-02-13","arxiv_id":"2302.06605","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/uniadapter-unified-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2302.06605","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.06605"}},"official":{"repos":["rerv/uniadapter","uniadapter/uniadapter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flexivit-one-model-for-all-patch-sizes","slug":"flexivit-one-model-for-all-patch-sizes","title":"FlexiViT: One Model for All Patch Sizes","date":"2022-12-15","arxiv_id":"2212.08013","repositories_listed":6,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/flexivit-one-model-for-all-patch-sizes#ran","syntology_url":"https://syntology.ai/paper/2212.08013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08013"}},"official":{"repos":["google-research/big_vision"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/are-multimodal-models-robust-to-image-and","slug":"are-multimodal-models-robust-to-image-and","title":"Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift","date":"2022-12-15","arxiv_id":"2212.08044","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/are-multimodal-models-robust-to-image-and#ran","syntology_url":"https://syntology.ai/paper/2212.08044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.08044"}},"official":null}},{"url":"/paper/efficient-vision-language-pretraining-with","slug":"efficient-vision-language-pretraining-with","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","date":"2022-08-29","arxiv_id":"2208.13628","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-vision-language-pretraining-with#ran","syntology_url":"https://syntology.ai/paper/2208.13628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.13628"}},"official":{"repos":["mshukor/vicha"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/coarse-to-fine-vision-language-pre-training","slug":"coarse-to-fine-vision-language-pre-training","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","date":"2022-06-15","arxiv_id":"2206.07643","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/coarse-to-fine-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2206.07643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07643"}},"official":{"repos":["microsoft/fiber"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/cross-view-language-modeling-towards-unified","slug":"cross-view-language-modeling-towards-unified","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","date":"2022-06-01","arxiv_id":"2206.00621","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-view-language-modeling-towards-unified#ran","syntology_url":"https://syntology.ai/paper/2206.00621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00621"}},"official":{"repos":["zengyan-97/cclm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","slug":"zero-and-r2d2-a-large-scale-chinese-cross","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","date":"2022-05-08","arxiv_id":"2205.03860","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/zero-and-r2d2-a-large-scale-chinese-cross#ran","syntology_url":"https://syntology.ai/paper/2205.03860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.03860"}},"official":{"repos":["yuxie11/R2D2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-pre-training-with-triple","slug":"vision-language-pre-training-with-triple","title":"Vision-Language Pre-Training with Triple Contrastive Learning","date":"2022-02-21","arxiv_id":"2202.10401","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vision-language-pre-training-with-triple#ran","syntology_url":"https://syntology.ai/paper/2202.10401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.10401"}},"official":{"repos":["uta-smile/TCL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wukong-100-million-large-scale-chinese-cross","slug":"wukong-100-million-large-scale-chinese-cross","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","date":"2022-02-14","arxiv_id":"2202.06767","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/wukong-100-million-large-scale-chinese-cross#ran","syntology_url":"https://syntology.ai/paper/2202.06767","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.06767"}},"official":null}},{"url":"/paper/multi-stage-pre-training-over-simplified","slug":"multi-stage-pre-training-over-simplified","title":"Multi-stage Pre-training over Simplified Multimodal Pre-training Models","date":"2021-07-22","arxiv_id":"2107.14596","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/multi-stage-pre-training-over-simplified#ran","syntology_url":"https://syntology.ai/paper/2107.14596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14596"}},"official":{"repos":["lttsmn/LXMERT-S"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","repositories_listed":6,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/align-before-fuse-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.07651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07651"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-relation-alignment-for-calibrated","slug":"learning-relation-alignment-for-calibrated","title":"Learning Relation Alignment for Calibrated Cross-modal Retrieval","date":"2021-05-28","arxiv_id":"2105.13868","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-relation-alignment-for-calibrated#ran","syntology_url":"https://syntology.ai/paper/2105.13868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.13868"}},"official":{"repos":["lancopku/IAIS"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lightningdot-pre-training-visual-semantic","slug":"lightningdot-pre-training-visual-semantic","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","date":"2021-03-16","arxiv_id":"2103.08784","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lightningdot-pre-training-visual-semantic#ran","syntology_url":"https://syntology.ai/paper/2103.08784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.08784"}},"official":{"repos":["intersun/LightningDOT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/scaling-up-visual-and-vision-language","slug":"scaling-up-visual-and-vision-language","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","date":"2021-02-11","arxiv_id":"2102.05918","repositories_listed":5,"syntology":{"n":10,"n_ran":8,"n_constructed":6,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/scaling-up-visual-and-vision-language#ran","syntology_url":"https://syntology.ai/paper/2102.05918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.05918"}},"official":null}},{"url":"/paper/graph-optimal-transport-for-cross-domain","slug":"graph-optimal-transport-for-cross-domain","title":"Graph Optimal Transport for Cross-Domain Alignment","date":"2020-06-26","arxiv_id":"2006.14744","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":6,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graph-optimal-transport-for-cross-domain#ran","syntology_url":"https://syntology.ai/paper/2006.14744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14744"}},"official":{"repos":["LiqunChen0606/Graph-Optimal-Transport"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/large-scale-adversarial-training-for-vision","slug":"large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":12,"n_constructed":5,"n_ran_checked":9,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/large-scale-adversarial-training-for-vision#ran","syntology_url":"https://syntology.ai/paper/2006.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06195"}},"official":{"repos":["zhegan27/LXMERT-AdvTrain","zhegan27/VILLA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/imram-iterative-matching-with-recurrent","slug":"imram-iterative-matching-with-recurrent","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","date":"2020-03-08","arxiv_id":"2003.03772","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/imram-iterative-matching-with-recurrent#ran","syntology_url":"https://syntology.ai/paper/2003.03772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.03772"}},"official":{"repos":["HuiChen24/IMRAM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-scene-graph-matching-for","slug":"cross-modal-scene-graph-matching-for","title":"Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrieval","date":"2019-10-11","arxiv_id":"1910.05134","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cross-modal-scene-graph-matching-for#ran","syntology_url":"https://syntology.ai/paper/1910.05134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.05134"}},"official":null}},{"url":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}},"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/the-neuro-symbolic-concept-learner-1","slug":"the-neuro-symbolic-concept-learner-1","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","date":"2019-04-26","arxiv_id":"1904.12584","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-neuro-symbolic-concept-learner-1#ran","syntology_url":"https://syntology.ai/paper/1904.12584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12584"}},"official":{"repos":["vacancy/NSCL-PyTorch-Release"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"464a4158100b480a9f548402b00255a1abfc5a94f61c495944569ab68c81e006","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}